perf: arm_spe: Add support for FEAT_SPE_EFT extended filtering

FEAT_SPE_EFT (optional from Armv9.4) adds mask bits for the existing
load, store and branch filters. It also adds two new filter bits for
SIMD and floating point with their own associated mask bits. The current
filters only allow OR filtering on samples that are load OR store etc,
and the new mask bits allow setting part of the filter to an AND, for
example filtering samples that are store AND SIMD. With mask bits set to
0, the OR behavior is preserved, so the unless any masks are explicitly
set old filters will behave the same.

Add them all and make them behave the same way as existing format bits,
hidden and return EOPNOTSUPP if set when the feature doesn't exist.

Reviewed-by: Leo Yan <[email protected]>
Tested-by: Leo Yan <[email protected]>
Signed-off-by: James Clark <[email protected]>
Signed-off-by: Will Deacon <[email protected]>

Author: james-c-linaro

drivers/perf/arm_spe_pmu.c

@@ -86,6 +86,7 @@ struct arm_spe_pmu {
 #define SPE_PMU_FEAT_ERND			(1UL << 5)
 #define SPE_PMU_FEAT_INV_FILT_EVT		(1UL << 6)
 #define SPE_PMU_FEAT_DISCARD			(1UL << 7)
+#define SPE_PMU_FEAT_EFT			(1UL << 8)
 #define SPE_PMU_FEAT_DEV_PROBED			(1UL << 63)
 	u64					features;
 
@@ -216,6 +217,27 @@ static const struct attribute_group arm_spe_pmu_cap_group = {
 #define ATTR_CFG_FLD_discard_CFG		config	/* PMBLIMITR_EL1.FM = DISCARD */
 #define ATTR_CFG_FLD_discard_LO			35
 #define ATTR_CFG_FLD_discard_HI			35
+#define ATTR_CFG_FLD_branch_filter_mask_CFG	config	/* PMSFCR_EL1.Bm */
+#define ATTR_CFG_FLD_branch_filter_mask_LO	36
+#define ATTR_CFG_FLD_branch_filter_mask_HI	36
+#define ATTR_CFG_FLD_load_filter_mask_CFG	config	/* PMSFCR_EL1.LDm */
+#define ATTR_CFG_FLD_load_filter_mask_LO	37
+#define ATTR_CFG_FLD_load_filter_mask_HI	37
+#define ATTR_CFG_FLD_store_filter_mask_CFG	config	/* PMSFCR_EL1.STm */
+#define ATTR_CFG_FLD_store_filter_mask_LO	38
+#define ATTR_CFG_FLD_store_filter_mask_HI	38
+#define ATTR_CFG_FLD_simd_filter_CFG		config	/* PMSFCR_EL1.SIMD */
+#define ATTR_CFG_FLD_simd_filter_LO		39
+#define ATTR_CFG_FLD_simd_filter_HI		39
+#define ATTR_CFG_FLD_simd_filter_mask_CFG	config	/* PMSFCR_EL1.SIMDm */
+#define ATTR_CFG_FLD_simd_filter_mask_LO	40
+#define ATTR_CFG_FLD_simd_filter_mask_HI	40
+#define ATTR_CFG_FLD_float_filter_CFG		config	/* PMSFCR_EL1.FP */
+#define ATTR_CFG_FLD_float_filter_LO		41
+#define ATTR_CFG_FLD_float_filter_HI		41
+#define ATTR_CFG_FLD_float_filter_mask_CFG	config	/* PMSFCR_EL1.FPm */
+#define ATTR_CFG_FLD_float_filter_mask_LO	42
+#define ATTR_CFG_FLD_float_filter_mask_HI	42
 
 #define ATTR_CFG_FLD_event_filter_CFG		config1	/* PMSEVFR_EL1 */
 #define ATTR_CFG_FLD_event_filter_LO		0
@@ -234,8 +256,15 @@ GEN_PMU_FORMAT_ATTR(pa_enable);
 GEN_PMU_FORMAT_ATTR(pct_enable);
 GEN_PMU_FORMAT_ATTR(jitter);
 GEN_PMU_FORMAT_ATTR(branch_filter);
+GEN_PMU_FORMAT_ATTR(branch_filter_mask);
 GEN_PMU_FORMAT_ATTR(load_filter);
+GEN_PMU_FORMAT_ATTR(load_filter_mask);
 GEN_PMU_FORMAT_ATTR(store_filter);
+GEN_PMU_FORMAT_ATTR(store_filter_mask);
+GEN_PMU_FORMAT_ATTR(simd_filter);
+GEN_PMU_FORMAT_ATTR(simd_filter_mask);
+GEN_PMU_FORMAT_ATTR(float_filter);
+GEN_PMU_FORMAT_ATTR(float_filter_mask);
 GEN_PMU_FORMAT_ATTR(event_filter);
 GEN_PMU_FORMAT_ATTR(inv_event_filter);
 GEN_PMU_FORMAT_ATTR(min_latency);
@@ -247,8 +276,15 @@ static struct attribute *arm_spe_pmu_formats_attr[] = {
 	&format_attr_pct_enable.attr,
 	&format_attr_jitter.attr,
 	&format_attr_branch_filter.attr,
+	&format_attr_branch_filter_mask.attr,
 	&format_attr_load_filter.attr,
+	&format_attr_load_filter_mask.attr,
 	&format_attr_store_filter.attr,
+	&format_attr_store_filter_mask.attr,
+	&format_attr_simd_filter.attr,
+	&format_attr_simd_filter_mask.attr,
+	&format_attr_float_filter.attr,
+	&format_attr_float_filter_mask.attr,
 	&format_attr_event_filter.attr,
 	&format_attr_inv_event_filter.attr,
 	&format_attr_min_latency.attr,
@@ -269,6 +305,16 @@ static umode_t arm_spe_pmu_format_attr_is_visible(struct kobject *kobj,
 	if (attr == &format_attr_inv_event_filter.attr && !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT))
 		return 0;
 
+	if ((attr == &format_attr_branch_filter_mask.attr ||
+	     attr == &format_attr_load_filter_mask.attr ||
+	     attr == &format_attr_store_filter_mask.attr ||
+	     attr == &format_attr_simd_filter.attr ||
+	     attr == &format_attr_simd_filter_mask.attr ||
+	     attr == &format_attr_float_filter.attr ||
+	     attr == &format_attr_float_filter_mask.attr) &&
+	     !(spe_pmu->features & SPE_PMU_FEAT_EFT))
+		return 0;
+
 	return attr->mode;
 }
 
@@ -364,8 +410,15 @@ static u64 arm_spe_event_to_pmsfcr(struct perf_event *event)
 	u64 reg = 0;
 
 	reg |= FIELD_PREP(PMSFCR_EL1_LD, ATTR_CFG_GET_FLD(attr, load_filter));
+	reg |= FIELD_PREP(PMSFCR_EL1_LDm, ATTR_CFG_GET_FLD(attr, load_filter_mask));
 	reg |= FIELD_PREP(PMSFCR_EL1_ST, ATTR_CFG_GET_FLD(attr, store_filter));
+	reg |= FIELD_PREP(PMSFCR_EL1_STm, ATTR_CFG_GET_FLD(attr, store_filter_mask));
 	reg |= FIELD_PREP(PMSFCR_EL1_B, ATTR_CFG_GET_FLD(attr, branch_filter));
+	reg |= FIELD_PREP(PMSFCR_EL1_Bm, ATTR_CFG_GET_FLD(attr, branch_filter_mask));
+	reg |= FIELD_PREP(PMSFCR_EL1_SIMD, ATTR_CFG_GET_FLD(attr, simd_filter));
+	reg |= FIELD_PREP(PMSFCR_EL1_SIMDm, ATTR_CFG_GET_FLD(attr, simd_filter_mask));
+	reg |= FIELD_PREP(PMSFCR_EL1_FP, ATTR_CFG_GET_FLD(attr, float_filter));
+	reg |= FIELD_PREP(PMSFCR_EL1_FPm, ATTR_CFG_GET_FLD(attr, float_filter_mask));
 
 	if (reg)
 		reg |= PMSFCR_EL1_FT;
@@ -767,6 +820,16 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
 	    !(spe_pmu->features & SPE_PMU_FEAT_FILT_LAT))
 		return -EOPNOTSUPP;
 
+	if ((FIELD_GET(PMSFCR_EL1_LDm, reg) ||
+	     FIELD_GET(PMSFCR_EL1_STm, reg) ||
+	     FIELD_GET(PMSFCR_EL1_Bm, reg) ||
+	     FIELD_GET(PMSFCR_EL1_SIMD, reg) ||
+	     FIELD_GET(PMSFCR_EL1_SIMDm, reg) ||
+	     FIELD_GET(PMSFCR_EL1_FP, reg) ||
+	     FIELD_GET(PMSFCR_EL1_FPm, reg)) &&
+	    !(spe_pmu->features & SPE_PMU_FEAT_EFT))
+		return -EOPNOTSUPP;
+
 	if (ATTR_CFG_GET_FLD(&event->attr, discard) &&
 	    !(spe_pmu->features & SPE_PMU_FEAT_DISCARD))
 		return -EOPNOTSUPP;
@@ -1058,6 +1121,9 @@ static void __arm_spe_pmu_dev_probe(void *info)
 	if (spe_pmu->pmsver >= ID_AA64DFR0_EL1_PMSVer_V1P2)
 		spe_pmu->features |= SPE_PMU_FEAT_DISCARD;
 
+	if (FIELD_GET(PMSIDR_EL1_EFT, reg))
+		spe_pmu->features |= SPE_PMU_FEAT_EFT;
+
 	/* This field has a spaced out encoding, so just use a look-up */
 	fld = FIELD_GET(PMSIDR_EL1_INTERVAL, reg);
 	switch (fld) {